Combining Human Perception and Geometric Restrictions for Automatic Pedestrian Detection

  • M. Castrillón-Santana
  • Q. C. Vuong
Conference paper

DOI: 10.1007/11881216_18

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4177)
Cite this paper as:
Castrillón-Santana M., Vuong Q.C. (2006) Combining Human Perception and Geometric Restrictions for Automatic Pedestrian Detection. In: Marín R., Onaindía E., Bugarín A., Santos J. (eds) Current Topics in Artificial Intelligence. CAEPIA 2005. Lecture Notes in Computer Science, vol 4177. Springer, Berlin, Heidelberg

Abstract

Automatic detection systems do not perform as well as human observers, even on simple detection tasks. A potential solution to this problem is training vision systems on appropriate regions of interests (ROIs), in contrast to training on predefined and arbitrarily selected regions. Here we focus on detecting pedestrians in static scenes. Our aim is to answer the following question: Can automatic vision systems for pedestrian detection be improved by training them on perceptually-defined ROIs?

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • M. Castrillón-Santana
    • 1
  • Q. C. Vuong
    • 2
  1. 1.IUSIANI, Edificio Central del Parque Científico-Tecnológico, Campus Universitario de TafiraUniversidad de Las Palmas de Gran CanariaLas PalmasSpain
  2. 2.Max Planck Institute for Biological CyberneticsCognitive & Computational PsychophysicsTübingenGermany

Personalised recommendations